Visual SLAM Framework Based on Segmentation with the Improvement of Loop Closure Detection in Dynamic Environments

Abstract

Most simultaneous localization and mapping (SLAM) systems assume that SLAM is conducted in a static environment. When SLAM is used in dynamic envi¬ronments, the accuracy of each part of the SLAM sys¬tem is adversely affected. We term this problem as dynamic SLAM. In this study, we propose solutions for three main problems in dynamic SLAM: Cam¬era tracking, three-dimensional map reconstruction, and loop closure detection. We propose to employ geometry-based method, deep learning-based method, and the combination of them for object segmenta¬tion. Using the information from segmentation to generate the mask, we filter the keypoints that lead to errors in visual odometry and features extracted by the CNN from dynamic areas to improve the per¬formance of loop closure detection. Then, we vali¬date our proposed loop closure detection method using the precision-recall curve and also confirm the frame¬work’s performance using multiple datasets. The ab¬solute trajectory error and relative pose error are used as metrics to evaluate the accuracy of the proposed SLAM framework in comparison with state-of-the-art methods. The findings of this study can potentially improve the robustness of SLAM technology in situa¬tions where mobile robots work together with humans, while the object-based point cloud byproduct has po¬tential for other robotics tasks.